A new approach for the recognition of images using a two dimensional array of Hopfield neural networks is presented in this paper. In the proposed method, the N/spl times/N image is divided into sub-blocks of size M/spl times/M. Two-dimensional Hopfield neural networks of size M/spl times/M are used to learn and recognize the sub-images. All the N/sup 2//M/sup 2/ Hopfield modules are functioning independently and are capable of recognizing the corrupted image successfully when they work together. It is shown mathematically that the network system converges in all circumstances. The performance of the proposed technique is evaluated by applying it into various binary and gray scale images. The gray scale images are treated in a three-dimensional perspective by considering an 8-bit gray scale image as 8 independent binary images. Eight layers of binary networks are used for the recognition purpose. A Fuzzy-ART based neural network is used for the classification and labeling of the outputs in the Hopfield network. By employing the new approach, it can be seen that the storage capacity of the entire pattern recognition system would be increased to 2/sup n/ where n=N/sup 2//M/sup 2/. Experiments conducted on different images of various sizes have shown that the proposed network structure can learn and recognize images even with 30% noise. In addition, the number of iterations required for the convergence of the network is significantly reduced and the number of synaptic weights required for the entire architecture is reduced from N/sup 4/ to N/sup 2/M/sup 2/. The proposed network structure is suitable for building dedicated hardware to enable the pattern recognition in real-time due to the requirement of less number of registers to store synaptic weights and reduced number of interconnections between neurons.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    High storage capacity architecture for pattern recognition using an array of Hopfield neural networks


    Beteiligte:
    Ming-Jung Seow, (Autor:in) / Asari, V.K. (Autor:in)


    Erscheinungsdatum :

    2001-01-01


    Format / Umfang :

    680569 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    High Storage Capacity Architecture for Pattern Recognition Using an Array of Hopfield Neural Networks

    Seow, M.-J. / Asari, V. K. | British Library Conference Proceedings | 2001


    Pattern recognition by homomorphic graph matching using Hopfield neural networks

    Suganthan, P. N. / Teoh, E. K. / Mital, D. P. | British Library Online Contents | 1995


    Object Recognition Using Multi-Layer Hopfield Neural Network

    Young, S. S. / Scott, P. D. / Nasrabadi, N. M. et al. | British Library Conference Proceedings | 1994


    On Recognition Capability of Hopfield Networks

    Koshelev, V. N. / Kryzhanovsky, B. V. | British Library Online Contents | 2001


    Photonic implementation of Hopfield neural network for associative pattern recognition [4417-75]

    Munshi, S. / Bhattacharyya, S. / Datta, A. K. et al. | British Library Conference Proceedings | 2001